Go back to Group.array() following zarr-developers/zarr-python#2667

Author: tomwhite

bio2zarr/plink.py

@@ -86,7 +86,7 @@ def convert(
     # we're not using the best Blosc settings for genotypes here.
     default_compressor = numcodecs.Blosc(cname="zstd", clevel=7)
 
-    a = root.create_dataset(
+    a = root.array(
         "sample_id",
         data=bed.iid,
         shape=bed.iid.shape,
@@ -99,7 +99,7 @@ def convert(
 
     # TODO encode these in slices - but read them in one go to avoid
     # fetching repeatedly from bim file
-    a = root.create_dataset(
+    a = root.array(
         "variant_position",
         data=bed.bp_position,
         shape=bed.bp_position.shape,
@@ -111,7 +111,7 @@ def convert(
     logger.debug("encoded variant_position")
 
     alleles = np.stack([bed.allele_1, bed.allele_2], axis=1)
-    a = root.create_dataset(
+    a = root.array(
         "variant_allele",
         data=alleles,
         shape=alleles.shape,

bio2zarr/vcf2zarr/vcz.py

@@ -572,7 +572,7 @@ def init(
     def encode_samples(self, root):
         if self.schema.samples != self.icf.metadata.samples:
             raise ValueError("Subsetting or reordering samples not supported currently")
-        array = root.create_dataset(
+        array = root.array(
             "sample_id",
             data=[sample.id for sample in self.schema.samples],
             shape=len(self.schema.samples),
@@ -584,7 +584,7 @@ def encode_samples(self, root):
         logger.debug("Samples done")
 
     def encode_contig_id(self, root):
-        array = root.create_dataset(
+        array = root.array(
             "contig_id",
             data=[contig.id for contig in self.schema.contigs],
             shape=len(self.schema.contigs),
@@ -593,7 +593,7 @@ def encode_contig_id(self, root):
         )
         array.attrs["_ARRAY_DIMENSIONS"] = ["contigs"]
         if all(contig.length is not None for contig in self.schema.contigs):
-            array = root.create_dataset(
+            array = root.array(
                 "contig_length",
                 data=[contig.length for contig in self.schema.contigs],
                 shape=len(self.schema.contigs),
@@ -605,7 +605,7 @@ def encode_contig_id(self, root):
     def encode_filter_id(self, root):
         # TODO need a way to store description also
         # https://github.com/sgkit-dev/vcf-zarr-spec/issues/19
-        array = root.create_dataset(
+        array = root.array(
             "filter_id",
             data=[filt.id for filt in self.schema.filters],
             shape=len(self.schema.filters),
@@ -955,7 +955,7 @@ def create_index(self):
         kwargs = {}
         if not zarr_v3():
             kwargs["dimension_separator"] = self.metadata.dimension_separator
-        array = root.create_dataset(
+        array = root.array(
             "region_index",
             data=index,
             shape=index.shape,